July 30, 2025
5 min read
Anirban Ghoshal
Google launches a new toolset to connect AI agents with BigQuery, enhancing enterprise data querying and metadata access.
Google has rolled out a new toolset designed to empower enterprises by enabling their AI agents to directly access and interact with data stored in BigQuery. This development addresses the escalating demand for sophisticated agentic applications, which are capable of performing tasks autonomously without continuous human oversight. The integration aims to enhance the accuracy and effectiveness of these AI agents by providing them with direct access to enterprise data, thereby enriching their contextual understanding.
The suite of tools includes several key functionalities for seamless BigQuery interaction:
- listdatasetids: This tool retrieves all dataset identifiers within a specified Google Cloud project.
- getdatasetinfo: It provides detailed metadata for a particular dataset.
- listtableids: This function lists all table identifiers within a selected dataset.
- gettableinfo: It fetches metadata for individual tables.
- execute_sql: This capability allows for the direct execution of SQL queries within BigQuery and the retrieval of their results. Crucially, this toolset is not a standalone solution. Enterprises must integrate it with Google's open-source offerings: the Agent Development Kit (ADK) and the MCP Toolbox for Databases (formerly known as the Generative AI Toolbox for Databases). To utilize the ADK, the toolset must be assigned to an agent created within the ADK framework. This is typically done by importing the toolset from the
- AI Agents Capabilities, Risks, and Growing Role
- How to Use Google Gemini for Smarter Crypto Trading
- AI-Powered Crypto Scams Surge: Experts Warn No One Is Safe
- The Future of Business Automation and Customer Engagement with AI Agents
agents.tools module in a Python environment via the ADK's command-line interface (CLI) or software development kit (SDK). The tool_filter parameter offers flexibility by allowing developers to specify which tools are exposed to the agent.
The MCP Toolbox for Databases offers native support for BigQuery's pre-built toolset. To access these tools, enterprises need to create a new mcp-toolbox folder in the same directory as their ADK-developed agentic application and install the MCP Toolbox within a Python-supported environment. Google also allows for the definition of custom SQL tools within the MCP Toolbox deployment.
According to Charlie Dai, vice president and principal analyst at Forrester, this integration is significant as it "provides pre-built frameworks to connect AI agents directly to BigQuery data. This eliminates custom integration work, reducing development overhead, and enables agents to leverage enterprise context for accurate responses." This advancement places Google alongside competitors like Databricks, Snowflake, and Teradata in expanding the MCP ecosystem for AI agent data connectivity. Google has indicated plans for future expansion of the toolset, though a specific timeline for new tools has not been announced.
Source: Google’s new toolset to help connect AI agents to BigQuery
Frequently Asked Questions (FAQ)
BigQuery and AI Agent Integration
Q: What is the primary purpose of Google's new toolset for BigQuery? A: The toolset is designed to enable AI agents to connect directly to data stored in BigQuery, facilitating the development of more context-aware and autonomous agentic applications. Q: What are the key tools included in this BigQuery toolset? A: The toolset includeslist<em>dataset</em>ids, get<em>dataset</em>info, list<em>table</em>ids, get<em>table</em>info, and execute_sql for interacting with BigQuery data.
Q: Can this toolset be used independently?
A: No, the toolset must be used in conjunction with Google's Agent Development Kit (ADK) and the MCP Toolbox for Databases.
Q: How do AI agents use these BigQuery tools?
A: Enterprises integrate these tools within frameworks like the ADK, assigning them to agents to access and query BigQuery data, thereby enhancing the agent's capabilities and accuracy.
Q: What is an "agentic application"?
A: An agentic application is an AI application that can perform tasks autonomously without requiring constant manual intervention from a user.
Q: Why is connecting AI agents to enterprise data important?
A: Connecting AI agents to enterprise data, such as that in BigQuery, provides them with crucial context, leading to more accurate responses and more effective task execution.
Q: Which other companies are offering similar solutions for AI agent data connectivity?
A: Competitors like Databricks, Snowflake, and Teradata have also launched offerings to connect AI agents to their respective data platforms.